@Lonely__MH: Announcing something: DeepSeek v4 is the undisputed god of Chinese writing! Personally tested Opus 4.8 and DeepSeek-v4-pro head-to-head. Result: Opus 4.8 got completely crushed. This proves that for Chinese writing, you've got to go with the homegrown champion! Paying respects to Master Liang
Summary
A personal test claims DeepSeek v4 surpasses Opus 4.8 in Chinese writing, asserting that DeepSeek v4 is currently the strongest model for Chinese writing.
View Cached Full Text
Cached at: 05/29/26, 12:05 PM
Announcement: DeepSeek V4 is absolutely the god of Chinese writing!
I personally tested Opus 4.8 and DeepSeek-v4-pro head-to-head.
Result: Opus 4.8 got completely wrecked.
It turns out that when it comes to Chinese, you still need the homegrown champion!
Bow to Saint Liang 🙃 https://t.co/zJqPlYjusJ
Lonely (@Lonely__MH): Fine, I’ll just tell you all.
DeepSeek V4 is the best at Chinese writing right now!
Everything else is garbage.
Similar Articles
@TheGeorgePu: I'm trying out DeepSeek V4 Pro, and really like it. Super underrated model. As good as Opus 4.8 from the few tests I ra…
User @TheGeorgePu praises DeepSeek V4 Pro, calling it underrated and comparing it favorably to Opus 4.8 based on initial tests.
@FuckAnthropic: Conducted a comparative analysis. Overall, DeepSeek V4 Flash-0731 is roughly a model at the level between Opus 4.7 and 4.8, entering the frontier Agent model competition with a minimal activation scale, and at about 1/12 to 1/60 of the token cost to enter the frontier Ag…
The author's comparative analysis concludes that DeepSeek V4 Flash-0731 achieves Opus 4.7–4.8 level performance with an extremely small activation scale, entering the frontier agent model tier at a very low token cost. It surpasses GLM-5.2 overall, but its shortfalls remain difficult repository-level coding and long-horizon engineering.
@10xmylife: Is DeepSeek V4.1 Flash for real? Just absolutely destroyed everything, damn
A user expressed surprise at the release and performance of DeepSeek V4.1 Flash, saying it delivered extremely strong results and sparking discussion in the community.
DeepSeek-V4-Flash has been updated, "The official release of DeepSeek-V4-Pro will follow soon"
DeepSeek 宣布更新了 DeepSeek-V4-Flash，并预告 DeepSeek-V4-Pro 的正式发布将很快到来。
@FinanceYF5: DeepSeek V4 Flash official API has now entered public beta. Key Agent capability upgrades: Terminal Bench 2.1 reaches 82.7, DeepSWE reaches 54.4, significantly surpassing V4 Pro Preview on multiple metrics, and approaching Opus 4.8. ...
DeepSeek V4 Flash official API enters public beta, with major Agent capability improvements (Terminal Bench 2.1 reaches 82.7, DeepSWE reaches 54.4), approaching Opus 4.8, and natively supports the Responses API format.